US11786656B2ActiveUtilityA1
Cloud big data-based system and method for insulin pump individualized configuration optimization
Assignee: MICROTECH MEDICAL HANGZHOU CO LTDPriority: Oct 12, 2017Filed: Oct 8, 2018Granted: Oct 17, 2023
Est. expiryOct 12, 2037(~11.3 yrs left)· nominal 20-yr term from priority
A61M 5/1723A61M 5/14276A61M 5/16877G16H 20/10G16H 20/17G16H 40/60A61M 2005/14252A61M 2005/14284A61M 2205/3553A61M 2205/3561A61M 2205/52A61M 2230/201A61M 5/142A61M 2005/14208A61M 2205/33G16H 50/70
38
PatentIndex Score
0
Cited by
32
References
6
Claims
Abstract
A cloud big data-based system and method for insulin pump individualized configuration optimization are provided. The system includes an insulin pump, a real-time continuous glucose monitoring system, a smart phone, a glucose monitoring application software installed in the smart phone and a cloud big data server. By means of personal blood glucose measurement historical data of users stored in the cloud, the insulin pump individualized configuration optimization system provides effective calculation of an individualized optimal insulin injection volume and injection rate for each user, thus aiding physicians and patients to formulate diabetes treatment plans with increased effectiveness.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1. A cloud big data-based system for insulin pump individualized configuration optimization, comprising an insulin pump, a real-time continuous glucose monitoring system (CGMS), a smart phone, a glucose monitoring application software installed in the smart phone, and a cloud big data server; wherein
the insulin pump comprises a syringe pump body with a control module and a wireless transmission module, a replaceable drug container and a subcutaneous indwelling needle; the wireless transmission module of the insulin pump is wirelessly connected to the smart phone and transmits data with the glucose monitoring application software;
the real-time continuous glucose monitoring system comprises a replaceable implantable glucose sensor probe, a reusable signal collector and a signal transmitter; the signal transmitter of the real-time continuous glucose monitoring system is wirelessly connected to the smart phone and transmits data with the glucose monitoring application software;
the smart phone and the glucose monitoring application software installed in the smart phone have a function of data transmission with the real-time continuous glucose monitoring system and the insulin pump through a wireless transmission technique, and a function of data upload and download through a smart phone data network or a wireless network from the cloud big data server;
the cloud big data server has functions of storing, updating, calculating and transmitting user's personal information and user's historical data;
the cloud big data server calculates user's personalized parameters related to diabetes according to the user's historical data stored in the cloud big data server to obtain calculated user's personalized parameters, and automatically corrects and calculates a parameter output data of the insulin pump and an implantable glucose sensor to obtain a corrected and calculated parameter output data, and transfers the calculated user's personalized parameters and the corrected and calculated parameter output data to the smart phone, the calculated user's personalized parameters and the corrected and calculated parameter output data comprise an amount CR of carbohydrate converted by 1 unit of insulin, an insulin sensitivity index IS, insulin retention time TA, a glucose release rate GR during fasting via metabolism, an injection volume BOLUS of a single high-dose injection and a basal infusion rate BASAL;
the insulin pump downloads the calculated user's personalized parameters and the corrected and calculated parameter output data from the cloud big data server through the smart phone, then calculates and recommends a high-dose insulin injection scheme according to a carbohydrate intake input by the user, and recommends an updated basal infusion rate scheme to the user according to a time segmentation of the basal infusion rate,
wherein a definition and a calculation method of the CR, the IS, the TA, the GR and an insulin infusion volume implemented in the cloud big data server includes the following:
CR: the amount of carbohydrate converted by 1 unit of insulin,
IS: the insulin sensitivity index,
TA: the insulin retention time,
GR: the glucose release rate during fasting via metabolism,
BOLUS: the injection volume of the single high-dose injection,
BASAL: the basal infusion rate, wherein the BASAL is counted in insulin units per hour (U/h), and
according to the CR, IS, TA, calculating the BOLUS is as follows:
BOLUS
=
CARBS
CR
+
BGcurrent
-
BGtarget
IS
-
BOLUSprev
(
1
-
min
(
TI
,
TA
)
TA
)
wherein, BGcurrent is a blood glucose value before a high-dose injection read by the real-time CGMS; BGtarget is a target blood glucose value; BOLUSprev is an injection volume of a previous high-dose injection; CARBS is a current carbohydrate intake input by the user; TI is a time between a current high-dose injection and a midpoint of the previous high-dose injection, min (TI, TA) is a smaller value of the TI and the TA, so that when the TI is greater than or equal to the TA, a residual amount of the previous high-dose injection
BOLUSprev
(
1
-
min
(
TI
,
TA
)
TA
)
is
0
,
and
according to the GR, calculating the BASAL during a fasting period (t) as follows:
BASAL
=
BGstart
-
BGtarget
+
GR
×
t
IS
-
BOLUSprev
(
1
-
min
(
TI
,
TA
)
TA
)
t
wherein, BGstart is an average blood glucose in a period after the fasting starts read by the real-time CGMS, and the TI is the time between the current high-dose injection and the midpoint of the previous high-dose injection.
2. The cloud big data-based system for insulin pump individualized configuration optimization according to claim 1 , wherein the user's personal information and the user's historical data stored in the cloud big data server comprise a name, a gender, an age, and a contact number of the user, a serial number of the insulin pump, records of an insulin pump infusion dose, an insulin pump infusion time and an insulin pump infusion rate, a blood glucose output value BG and a data measurement time (Ts) corresponding to the BG, the carbohydrate intake, a sleep and an exercise recorded by the user.
3. The cloud big data-based system for insulin pump individualized configuration optimization according to claim 1 , wherein the cloud big data server optimizes the CR, the IS, and the TA by collecting a real-time data obtained by the user using the real-time CGMS and the insulin pump for the high-dose injection, specific steps are as follows:
step A, establishing a regression equation
BGbefore
-
BGafter
=
(
BOLUS
+
BOLUSprev
)
IS
+
(
-
CARBS
)
IS
CR
+
(
-
BOLUSprev
×
min
(
TI
,
TA
)
)
IS
TA
wherein, BGbefore is the blood glucose value before the high-dose injection and equal to BGcurrent in the calculation formula for the BOLUS; BGafter is a measured blood glucose value after a period of the high-dose injection;
step B, obtaining the following data near each high-dose injection start time (Tstart) from the insulin pump and the real-time CGMS through the smart phone:
the injection start time Tstart: insulin pump data
an injection end time/Tend): insulin pump data
the injection volume BOLUS of the high-dose injection at the Tstart: insulin pump data
the blood glucose value BGbefore measured by the implantable glucose sensor at the Tstart
the blood glucose value BGafter measured by the implantable glucose sensor after a period of Tend
the carbohydrate intake CARBS input by the user near the Tstart
forming a sample record packet for a calculation
[ T start n T end n BOLUS n CARBS n BG before n BG after n ]
data in the last three to six months are used for a regression, a subscript number n of a historical data variable is arranged in reverse order of the Tstart;
step C, constructing a sample matrix:
G
=
[
Δ
BG
1
Δ
BG
2
Δ
BG
3
⋮
Δ
BG
n
]
X
=
[
BOLUS
1
′
-
CARBS
1
-
BOLUS
2
×
TI
1
′
BOLUS
2
′
-
CARBS
2
-
BOLUS
3
×
TI
2
′
BOLUS
3
′
-
CARBS
3
-
BOLUS
4
×
TI
3
′
⋮
⋮
⋮
BOLUS
n
′
-
CARBS
n
-
BOLUS
n
+
1
×
TI
n
′
]
wherein,
Δ BG n =BG after n −BG before n ,
when TI n <TAu, BOLUS′ n =BOLUS n +BOLUS n+1 , TI′ n =TI n ,
TI n =T start n −( T start n+1 +T end n+1 )/2;
when TI n >TAu, BOLUS′ n =BOLUS n , TI′ n =0;
when TAl≤TI n ≤TAu, the sample is abandoned;
TAu is an upper limit allowed by the TA, and TAl is a lower limit allowed by the TA;
step D, if for each n, X n,3 =0, then:
X
=
[
BOLUS
1
′
-
CARBS
1
BOLUS
2
′
-
CARBS
2
BOLUS
3
′
-
CARBS
3
⋮
⋮
BOLUS
n
′
-
CARBS
n
]
C
=
[
IS
IS
/
CR
]
otherwise, the sample matrix remains unchanged;
step E, solving an overdetermined equation G=XC,
a weighted least square method is used to solve: Ĉ=(X T WX) −1 X T WG;
step F, eliminating an abnormal data: calculating a residual error: {circumflex over (ε)}=G−XĈ, eliminating data items whose residual error is greater than a threshold, and then repeating a regression algorithm in the steps A-F until there are no data items whose residual error is greater than the threshold;
step G, calculating updated physiological parameters IS, CR, and TA according to results of the regression algorithm:
= Ĉ 1,1
= Ĉ 1,1 /Ĉ 2,1
if Ĉ 3,1 exists, then =Ĉ 1,1 /Ĉ 3,1 , otherwise =TA;
step H, finally, using the obtained , and to correct the currently set IS, CR and TA with a predetermined correction ratio γ, wherein a range of γ values is 0<γ<1,
IS :=(1−γ)× IS+γ×
CR :=(1−γ)× CR+γ×
TA :=(1−γ)× TA+γ×
the above is used as setting parameters for the high-dose injection of the insulin pump from now on;
TAl and TAu are revised at the same time:
TAl:=TA ×τ%, where 0<τ<100;
TAu:=TA ×υ%, where 100<υ<150;
storing and updating physiological parameters IS, CR, TA, TAl and TAu to the cloud big data server and pushing the physiological parameters to a mobile application and the insulin pump.
4. The cloud big data-based system for insulin pump individualized configuration optimization according to claim 1 , wherein the cloud big data server optimizes a value of physiological parameter GR in predetermined time periods and the corresponding basal infusion rate BASAL by collecting real-time data obtained by the user using the real-time CGMS and the insulin pump in real time, specific steps are as follows:
step A, first, segmenting 24 hours a day according to the basal infusion rate established by the user with reference to doctor's recommendations and his/her own situation, wherein the GR and the BASAL values in each time period need to be set and calculated independently, for each time period and 2 hours before the each time period, if the user eats something, and a high-dose injection accompanied with or without food is performed, data obtained at 2 hours after [a] meal or the high-dose injection needs to be excluded from the time period, data of the time period is updated to only include data of longer continuous time remaining after a removal of the data obtained at 2 hours after the meal/high-dose injection;
step B, collecting sample data in each valid time period:
Tstart: the start time of the time period
BGstart: an average value of blood glucose in a previous short period of the time period
BGend: an average value of blood glucose in a last short period of the time period
BASAL: the basal infusion rate during the time period
t: a duration of the time period
IS: the insulin sensitivity index
TA: the insulin retention time
RESIDUAL
=
BOLUSprev
(
1
-
min
(
TLTA
)
TA
)
:
residual insulin in the body at the beginning of the time period
SNR: a signal-to-noise ratio of dynamic blood glucose data
forming a sample record package for a calculation
[ T start n BG start n BG end n BASAL n t n RESIDUAL n SNR n ] and system parameters IS and TA;
data of the time period in the last three to six months are used for [a] regression, and the subscript number n of the historical data variables is arranged in reverse order of the Tstart;
step C, for each effective time period, considering an effectiveness of ingesting insulin, a total glucose ΔBG released by [a] body into the blood through metabolism is:
Δ BG n =BG end n −BG start n +[BASAL n ×t n +RESIDUAL n ]×IS
establishing a regression equation ΔBG=GR×t;
step D, for each valid time period, using a regression method to calculate an updated value of GR
=
∑
n
=
1
N
t
n
×
Δ
BG
n
×
SNR
n
×
w
(
T
n
′
)
∑
n
=
1
N
t
n
2
×
SNR
n
×
w
(
T
n
′
)
wherein, w(T′) is a first time-related weight, T′ n =Tcurrent−Tstart n , Tcurrent is the current time, that is, the time of the latest historical data Tstart 1 ;
step E, using the updated value to correct the currently set GR with a predetermined correction ratio γ
GR :=(1−γ)× GR+γ×
a range of γ values is 0<γ<1;
step F, using a modified GR and a historical sample packet [BGstart n t n RESIDUAL n ] of the time period to calculate value to be set in the time period a correction according to the formula:
=
BGstart
n
-
BGtarget
+
GR
×
t
n
IS
-
RESIDUAL
n
t
n
step G, weighting all the calculated in time to calculate a current BASAL correction value :
=
∑
n
=
1
N
×
w
′
(
T
n
′
)
∑
n
=
1
N
w
′
(
T
n
′
)
wherein, w′(T′) is a second time-related weight;
step H, if a difference between the calculated value and the current BASAL value exceeds the threshold, using the [calculated] to correct the currently set BASAL with a predetermined correction γ:
γ
:
BASAL
:=
(
1
-
γ
)
×
BASAL
+
γ
×
a range of γ values is 0<γ<1;
storing and updating the BASAL as a setting parameter of a basal injection rate of the insulin pump, and storing the BASAL to the cloud big data server together with the physiological parameter GR and push the BASAL and the GR to the mobile application and the insulin pump.
5. The cloud big data-based system for insulin pump individualized configuration optimization according to claim 1 , wherein the cloud big data server optimizes the basal infusion rate BASAL in predetermined time periods by collecting real-time data obtained by the user using the real-time CGMS and the insulin pump in real time, specific steps are as follows:
step A, first, segmenting 24 hours a day according to the basal infusion rate established by the user with reference to doctor's recommendations and his/her own situation, wherein the BASAL value in each time period needs to be set and calculated independently, for each time period and 2 hours before the each time period, if the user eats something, and a high-dose injection accompanied with or without food is performed, data obtained at 2 hours after [a] meal or the high-dose injection needs to be excluded from the time period, data in the time period is updated to include only data of the [longer] continuous time remaining after a removal of the data [obtained] at 2 hours after the eating/high-dose injection;
step B, collecting sample data in each valid time period:
the Tstart: the start time of the time period
the BGstart: the average value of blood glucose in a previous short period of the time period
BGend: an average value of blood glucose in a last short period of the time period
BASAL: basal infusion rate during the time period
t: a duration of the time period
IS: the insulin sensitivity index
TA: the insulin retention time
RESIDUAL
=
BOLUSprev
(
1
-
min
(
TLTA
)
TA
)
:
a residual insulin in [a] body at the beginning of the time period
forming a sample record package for a calculation
[ T start n BG start n BG end n BASAL n t n RESIDUAL n ] and system parameters IS and TA;
the data of the time period in the last three to six months are used for [a] regression, and the subscript number n of historical data variables is arranged in reverse order of the Tstart;
step C, for an n th time period, using a historical sample packet of the n th time period to calculate value to be set in the time period after a correction according to the formula:
=
BASAL
n
+
RESIDUAL
n
t
n
-
BGtarget
-
BGend
n
IS
×
t
n
step D, weighting all the calculated in time to calculate a current BASAL correction value :
=
∑
n
=
1
N
×
w
′
(
T
n
′
)
∑
n
=
1
N
w
′
(
T
n
′
)
wherein, w′(T′) is a time-related weight
Step E, if a difference between difference between the calculated value and the current BASAL value exceeds a threshold, using the [calculated] to correct the currently set BASAL with a predetermined correction ratio γ:
γ
:
BASAL
:=
(
1
-
γ
)
×
BASAL
+
γ
×
a range of γ values is 0<γ<1.
6. A cloud big data-based method for insulin pump individualized configuration optimization, comprising:
step 1, obtaining, by a smart phone application, a cloud big data server data when a system is started to determine whether a user is using an insulin injection system for the first time, if yes, prompting the user to set parameters insulin sensitivity index (IS), an amount of carbohydrate converted by 1 unit of insulin (CR), insulin retention time (TA), a glucose release rate (GR) during fasting via metabolism, time segmentation and a basal injection rate or to continue to use a default setting, if no, downloading updated parameters from a cloud big data server;
step 2, entering into a high-dose injection mode in response to the user inputting a high-dose injection command manually,
step 3, in the high-dose mode, the insulin pump prompting the user to manually enter a carbohydrate intake (CARBS) and confirm a target blood glucose value to be achieved through the smart phone application, while obtaining a current blood glucose value (BGcurrent) measured by a real-time continuous glucose monitoring system (CGMS);
step 4, calculating a required high-dose injection volume (BOLUS) using previously set or obtained parameter values:
BOLUS=CARBS/ CR +( BG current− BG target)/ IS −BOLUSprev[1−min( TI,TA )/ TA],
wherein BGtarget is a target blood glucose value, and BOLUSprev is an injection volume of a previous high-dose injection, TI is a time between a current high-dose injection and a midpoint of the previous high-dose injection, min (TI, TA) is a smaller value of the TI and the TA, so that when the TI is greater than or equal to the TA, a residual amount of the previous high-dose injection
BOLUSprev
(
1
-
min
(
TLTA
)
TA
)
is 0, and
calculating a basal infusion rate (BASAL), wherein the BASAL is counted in insulin units per hour (U/h), during a fasting period (t) as follows:
BASAL
=
BGstart
-
BGtarget
+
GR
×
t
IS
-
BOLUS
prev
(
1
-
min
(
TLTA
)
TA
)
t
wherein, BGstart is an average blood glucose in a period after the fasting starts read by the real-time CGMS;
step 5, prompting the user to confirm an infusion volume and a high-dose infusion time, and calculating an injection stop time Tend=Tstart+TBolus, wherein TBolus=infusion volume/bolus-rate, bolus-rate is a user-defined high-dose insulin infusion rate, and Tstart is an injection start time;
step 6, uploading insulin injection information Tstart, Tend, BOLUS, CARBS and CGMS blood glucose monitoring data to the cloud big data server;
step 7, downloading the insulin injection information at the insulin pump and performing the high-dose injection until the Tend is reached;
step 8, detecting whether there are physiological parameters updated in the cloud big data server, if yes, updating local storage parameters, and then repeating step 2; if no, repeating step 2 directly.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.